Continuous seasonal monitoring of nitrogen and water content in lettuce using a dual phenomics system.

The collection and analysis of large amounts of information on a plant-by-plant basis contributes to the development of precision fertigation and may be achieved by combining remote-sensing technology with high-throughput phenotyping methods. Here, lettuce plants (Lactuca sativa) were grown under optimal and suboptimal nitrogen and irrigation treatments from seedlings to harvest. A Plantarray system was used to calculate and log weights, daily transpiration, and momentary transpiration rates throughout the experiment. From 15 d after planting until experiment termination, the entire array of plants was imaged hourly (from 09.00 h to 14.00 h) using a hyperspectral moving camera. Three vegetation indices were calculated from the plants' reflectance signal: red-edge chlorophyll index (RECI), photochemical reflectance index (PRI), and water index (WI), and combined treatments, physiological measurements, and vegetation indices were compared. RECI values differed significantly between nitrogen treatments from the first day of imaging, and WI values distinguished well-irrigated from drought-treated groups before detecting significant differences in daily transpiration rate. The PRI, calculated hourly during the drought-treatment phase, changed with the momentary transpiration rate. Thus, hyperspectral imaging might be used in growing facilities to detect nitrogen or water shortages in plants before their physiological response affects yields.

vis-NIR and XRF Data Fusion and Feature Selection to Estimate Potentially Toxic Elements in Soil.

Soil contamination by potentially toxic elements (PTEs) is intensifying under increasing industrialization. Thus, the ability to efficiently delineate contaminated sites is crucial. Visible-near infrared (vis-NIR: 350-2500 nm) and X-ray fluorescence (XRF: 0.02-41.08 keV) spectroscopic techniques have attracted tremendous attention for the assessment of PTEs. Recently, the application of fused vis-NIR and XRF spectroscopy, which is based on the complementary effect of data fusion, is also increasing. Moreover, different data manipulation methods, including feature selection approaches, affect the prediction performance. This study investigated the feasibility of using single and fused vis-NIR and XRF spectra while exploring feature selection algorithms for the assessment of key soil PTEs. The soil samples were collected from one of the most heavily polluted areas of the Czech Republic and scanned using laboratory vis-NIR and XRF spectrometers. Univariate filter (UF) and genetic algorithm (GA) were used to select the bands of greater importance for the PTE prediction. Support vector machine (SVM) was then used to train the models using the full-range and feature-selected spectra of single sensors and their fusion. It was found that XRF spectra alone (primarily GA-selected) performed better than single vis-NIR and fused spectral data for predictions of PTEs. Moreover, the prediction models that were derived from the fused data set (particularly the GA-selected) enhanced the models' accuracies as compared with the single vis-NIR spectra. In general, the results suggest that the GA-selected spectra obtained from the single XRF spectrometer (for As and Pb) and from the fusion of vis-NIR and XRF (for Pb) are promising for accurate quantitative estimation detection of the mentioned PTEs.

Estimation of the Relative Abundance of Quartz to Clay Minerals Using the Visible-Near-Infrared-Shortwave-Infrared Spectral Region.

Quartz is the most abundant mineral on the earth's surface. It is spectrally active in the longwave infrared (LWIR) region with no significant spectral features in the optical domain, i.e., visible-near-infrared-shortwave-infrared (Vis-NIR-SWIR) region. Several space agencies are planning to mount optical image spectrometers in space, with one of their missions being to map raw materials. However, these sensors are active across the optical region, making the spectral identification of quartz mineral problematic. This study demonstrates that indirect relationships between the optical and LWIR regions (where quartz is spectrally dominant) can be used to assess quartz content spectrally using solely the optical region. To achieve this, we made use of the legacy Israeli soil spectral library, which characterizes arid and semiarid soils through comprehensive chemical and mineral analyses along with spectral measurements across the Vis-NIR-SWIR region (reflectance) and LWIR region (emissivity). Recently, a Soil Quartz Clay Mineral Index (SQCMI) was developed using mineral-related emissivity features to determine the content of quartz, relative to clay minerals, in the soil. The SQCMI was highly and significantly correlated with the Vis-NIR-SWIR spectral region (R2 = 0.82, root mean square error (RMSE) = 0.01, ratio of performance to deviation (RPD) = 2.34), whereas direct estimation of the quartz content using a gradient-boosting algorithm against the Vis-NIR-SWIR region provided poor results (R2 = 0.45, RMSE = 15.63, RPD = 1.32). Moreover, estimation of the SQCMI value was even more accurate when only the 2000-2450 nm spectral range (atmospheric window) was used (R2 = 0.9, RMSE = 0.005, RPD = 1.95). These results suggest that reflectance data across the 2000-2450 nm spectral region can be used to estimate quartz content, relative to clay minerals in the soil satisfactorily using hyperspectral remote sensing means.

Detection of Potassium Deficiency and Momentary Transpiration Rate Estimation at Early Growth Stages Using Proximal Hyperspectral Imaging and Extreme Gradient Boosting.

Potassium is a macro element in plants that is typically supplied to crops in excess throughout the season to avoid a deficit leading to reduced crop yield. Transpiration rate is a momentary physiological attribute that is indicative of soil water content, the plant's water requirements, and abiotic stress factors. In this study, two systems were combined to create a hyperspectral-physiological plant database for classification of potassium treatments (low, medium, and high) and estimation of momentary transpiration rate from hyperspectral images. PlantArray 3.0 was used to control fertigation, log ambient conditions, and calculate transpiration rates. In addition, a semi-automated platform carrying a hyperspectral camera was triggered every hour to capture images of a large array of pepper plants. The combined attributes and spectral information on an hourly basis were used to classify plants into their given potassium treatments (average accuracy = 80%) and to estimate transpiration rate (RMSE = 0.025 g/min, R2 = 0.75) using the advanced ensemble learning algorithm XGBoost (extreme gradient boosting algorithm). Although potassium has no direct spectral absorption features, the classification results demonstrated the ability to label plants according to potassium treatments based on a remotely measured hyperspectral signal. The ability to estimate transpiration rates for different potassium applications using spectral information can aid in irrigation management and crop yield optimization. These combined results are important for decision-making during the growing season, and particularly at the early stages when potassium levels can still be corrected to prevent yield loss.

Modelling potentially toxic elements in forest soils with vis-NIR spectra and learning algorithms.

The surface organic horizons in forest soils have been affected by air and soil pollutants, including potentially toxic elements (PTEs). Monitoring of PTEs requires a large number of samples and adequate analysis. Visible-near infrared (vis-NIR: 350-2500 nm) spectroscopy provides an alternative method to conventional laboratory measurements, which are time-consuming and expensive. However, vis-NIR spectroscopy relies on an empirical calibration of the target attribute to the spectra. This study examined the capability of vis-NIR spectra coupled with machine learning (ML) techniques (partial least squares regression (PLSR), support vector machine regression (SVMR), and random forest (RF)) and a deep learning (DL) approach called fully connected neural network (FNN) to assess selected PTEs (Cr, Cu, Pb, Zn, and Al) in forest organic horizons. The dataset consists of 2160 samples from 1080 sites in the forests over all the Czech Republic. At each site, we collected two samples from the fragmented (F) and humus (H) organic layers. The content of all PTEs was higher in horizon H compared to F horizon. Our results indicate that the reflectance of samples tended to decrease with increased PTEs concentration. Cr was the most accurately predicted element, regardless of the algorithm used. SVMR provided the best results for assessing the H horizon (R2 = 0.88 and RMSE = 3.01 mg/kg for Cr). FNN produced the best predictions of Cr in the combined F + H layers (R2 = 0.89 and RMSE = 2.95 mg/kg) possibly due to the larger number of samples. In the F horizon, the PTEs were not predicted adequately. The study shows that PTEs in forest soils of the Czech Republic can be accurately estimated with vis-NIR spectra and ML approaches. Results hint in availability of a large sample size, FNN provides better results.

An Innovative Approach to Exploit the Reflection Spectroscopy of Liquid Characteristics.

Reflection spectroscopy, in the visible-near-infrared-shortwave infrared region (Vis-NIR-SWIR, 350-2500 nm), is a useful technology to extract chemical and physical properties of materials, but might be useless in identifying the spectral features of transparent or dark opaque liquids. Low reflectance values of a liquid reduce the ability to identify characteristic absorption features at specific wavelengths in the reflectance spectrum. In this study, we present a rapid and easy-to-use method to increase the measured reflectance spectrum and expose characteristic absorption features of a liquid. This was done by mixing the liquid with a white enhanced substance (WES). For this purpose, we used aluminum oxide (Al2O3) powder-a very bright (high albedo) substance and featureless across the entire Vis-NIR-SWIR region. The reflectance spectrum of the mixture-liquid and WES-was measured using a spectroradiometer. This procedure enabled to identify characteristic spectral features of the liquids that would have not been observed in the reflectance spectrum measured from the liquid alone.

Quantitative assessment of hydrocarbon contamination in soil using reflectance spectroscopy: a "multipath" approach.

Petroleum hydrocarbons are contaminants of great significance. The commonly used analytic method for assessing total petroleum hydrocarbons (TPH) in soil samples is based on extraction with 1,1,2-Trichlorotrifluoroethane (Freon 113), a substance prohibited to use by the Environmental Protection Agency. During the past 20 years, a new quantitative methodology that uses the reflected radiation of solids has been widely adopted. By using this approach, the reflectance radiation across the visible, near infrared-shortwave infrared region (400-2500 nm) is modeled against constituents determined using traditional analytic chemistry methods and then used to predict unknown samples. This technology is environmentally friendly and permits rapid and cost-effective measurements of large numbers of samples. Thus, this method dramatically reduces chemical analytical costs and secondary pollution, enabling a new dimension of environmental monitoring. In this study we adapted this approach and developed effective steps in which hydrocarbon contamination in soils can be determined rapidly, accurately, and cost effectively solely from reflectance spectroscopy. Artificial contaminated samples were analyzed chemically and spectrally to form a database of five soils contaminated with three types of petroleum hydrocarbons (PHCs), creating 15 datasets of 48 samples each at contamination levels of 50-5000 wt% ppm (parts per million). A brute force preprocessing approach was used by combining eight different preprocessing techniques with all possible datasets, resulting in 120 different mutations for each dataset. The brute force was done based on an innovative computing system developed for this study. A new parameter for evaluating model performance scoring (MPS) is proposed based on a combination of several common statistical parameters. The effect of dividing the data into training validation and test sets on modeling accuracy is also discussed. The results of this study clearly show that predicting TPH levels at low concentrations in selected soils at high precision levels is viable. Dividing a dataset into training, validation, and test groups affects the modeling process, and different preprocessing methods, alone or in combination, need to be selected based on soil type and PHC type. MPS was found to be a better parameter for selecting the best performing model than ratio of prediction to deviation, yielding models with the same performance but less complicated and more stable. The use of the "all possibilities" system proved to be mandatory for efficient optimal modeling of reflectance spectroscopy data.

Water Productivity Mapping (WPM) Using Landsat ETM+ Data for the Irrigated Croplands of the Syrdarya River Basin in Central Asia.

The overarching goal of this paper was to espouse methods and protocols for water productivity mapping (WPM) using high spatial resolution Landsat remote sensing data. In a world where land and water for agriculture are becoming increasingly scarce, growing "more crop per drop" (increasing water productivity) becomes crucial for food security of future generations. The study used time-series Landsat ETM+ data to produce WPMs of irrigated crops, with emphasis on cotton in the Galaba study area in the Syrdarya river basin of Central Asia. The WPM methods and protocols using remote sensing data consisted of: (1) crop productivity (ton/ha) maps (CPMs) involvingcrop type classification, crop yield and biophysical modeling, and extrapolating yield models to larger areas using remotely sensed data; (2) crop water use (m³/ha) maps (WUMs) (or actual seasonal evapotranspiration or actual ET) developed through Simplified Surface Energy Balance (SSEB) model; and (3) water productivity (kg/m³) maps (WPMs) produced by dividing raster layers of CPMs by WUMs. The SSEB model calculated WUMs (actual ET) by multiplying the ET fractionby reference ET. The ETfraction was determined using Landsat thermal imagery by selecting the "hot" pixels (zero ET) and "cold" pixels (maximum ET). The grass reference ET was calculated by FAO Penman-Monteith method using meteorological data. The WPMs for the Galaba study area demonstrated a wide variations (0-0.54 kg/m³) in water productivity of cotton fields with overwhelming proportion (87%) of the area having WP less than 0.30 kg/m³, 11% of the area having WP in range of 0.30-0.36 kg/m³, and only 2% of the area with WP greater than 0.36 kg/m³. These results clearly imply that there are opportunities for significant WP increases in overwhelming proportion of the existing croplands. The areas of low WP are spatially pin-pointed and can be used as focus for WP improvements through better land and water management practices.